1 Loading required packages

knitr::opts_chunk$set(warning = FALSE, message = FALSE)
library(tidyverse)
library(sf)
library(tmap)
library(PerformanceAnalytics) #scatter plot matrix
library(PerformanceAnalytics) #scatter plot matrix
 
# Change the presentation of decimal numbers to 4 and avoid scientific notation
options(prompt="R> ", digits=5, scipen=999)

2 Import the shapefile

sh<- st_read("../../Data/city.shp")

Reading layer `City' from data source `C:\Users\felip\OneDrive\Desktop\Meidai\Seminar Research\GitHub\book-2020-spatial-analysis-methods-and-practice\Data\City.shp' using driver `ESRI Shapefile'
Simple feature collection with 90 features and 15 fields
geometry type:  POLYGON
dimension:      XY
bbox:           xmin: 472360 ymin: 4199900 xmax: 481460 ymax: 4209300
projected CRS:  GGRS87 / Greek Grid

object.size(sh)

140128 bytes

s.sp <- as(sh, "Spatial")
class(s.sp)

[1] "SpatialPolygonsDataFrame"
attr(,"package")
[1] "sp"

class(sh)

[1] "sf"         "data.frame"

2.1 Inspect the table within the shapefile

st_drop_geometry(sh)

2.2 A quick map

qtm(sh)

3 Creating the breaks for the custom breaks map

breaks<- c(-Inf, 15000,20000,25000, Inf)

3.1 creating the custom breaks map

tm_shape(sh) +
  tm_fill("Income", title= "Income",breaks=breaks,palette="Greens")+
  tm_borders()

4 Creating a histogram

sh %>% 
  ggplot(aes(x=Income))+
  geom_histogram(bins=10, color="black", fill="white")

5 creating a box plot

geom_jitter(size = 3, alpha = 0.3, width = 0.1) is used so that the points are not all crammed in the same line

set.seed(2019)
sh %>% 
  ggplot(aes(x=Income, y=Municipali))+
  geom_boxplot()+
  geom_jitter(size = 3, alpha = 0.3, width = 0.1)

6 Creating a new variable standardized income

sh$IncZScore<- as.vector(scale(sh$Income, center = TRUE, scale = TRUE))

6.1 creating the new breaks

breaks_Z<- c(-Inf, -2.5,-1, 1, 2.5, Inf)

6.2 creating the custom breaks map

#creating a vector with the colors for the bins in the map
col<- c('#ffffb2','#fecc5c','#fd8d3c','#f03b20','#bd0026')

tm_shape(sh) +
  tm_fill("IncZScore", title= "Standardized Income", breaks=breaks_Z, palette = col)+
  tm_borders()

7 Bivariate Analysis: Analyzing Expenditures by Educational Attainment

A scatter plot and the OLS regression estimates

sh %>% 
  ggplot(aes(x=University, y=Expenses))+
  geom_point()+
  geom_smooth(method = "lm")

lm.sh<-   lm(Expenses ~ University, data=sh)
summary( lm.sh)

Call:
lm(formula = Expenses ~ University, data = sh)

Residuals:
    Min      1Q  Median      3Q     Max 
-132.33  -29.14  -14.76    9.47  293.99 

Coefficients:
            Estimate Std. Error t value          Pr(>|t|)    
(Intercept)    15.69      19.17    0.82              0.42    
University      8.89       0.97    9.16 0.000000000000019 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 64.4 on 88 degrees of freedom
Multiple R-squared:  0.488, Adjusted R-squared:  0.482 
F-statistic: 83.9 on 1 and 88 DF,  p-value: 0.0000000000000193

8 Creating a scatter plot matrix

data<- data.frame( sh$Expenses, sh$University, sh$SecondaryE)
data

chart.Correlation(data, histogram = TRUE, method = "pearson")

8.1 A better option

#pairs.panels(data,
 #            smooth = TRUE,      # If TRUE, draws loess smooths
 #            scale = FALSE,      # If TRUE, scales the correlation text font
 #            density = TRUE,     # If TRUE, adds density plots and histograms
  #           ellipses = TRUE,    # If TRUE, draws ellipses
  #           method = "pearson", # Correlation method (also "spearman" or "kendall")
  #           pch = 21,           # pch symbol
  #           lm = TRUE,         # If TRUE, plots linear fit rather than the LOESS (smoothed) fit
  #           cor = TRUE,         # If TRUE, reports correlations
  #           jiggle = FALSE,     # If TRUE, data points are jittered
  #           factor = 2,         # Jittering factor
  #           hist.col = 4,       # Histograms color
  #           stars = TRUE,       # If TRUE, adds significance level with stars
  #           ci = TRUE)          # If TRUE, adds confidence intervals

That’s all!